SoK: Evaluating Jailbreak Guardrails for Large Language Models
Authors: Xunguang Wang, Zhenlan Ji, Wenxuan Wang, Zongjie Li, Daoyuan Wu, Shuai Wang | Published: 2025-06-12
安全性と有用性のトレードオフ
$\texttt{SAGE}$: A Generic Framework for LLM Safety Evaluation
Authors: Madhur Jindal, Hari Shrawgi, Parag Agrawal, Sandipan Dandapat | Published: 2025-04-28
Improving LLM Safety Alignment with Dual-Objective Optimization
Authors: Xuandong Zhao, Will Cai, Tianneng Shi, David Huang, Licong Lin, Song Mei, Dawn Song | Published: 2025-03-05 | Updated: 2025-06-12